{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:66CYTZEZEZ5UMV7PEXYAD7OHEX","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"3e19f4f348cc966c3c0d967c28789f1a92548a79fc983b9259ec253597ad8113","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-30T15:27:12Z","title_canon_sha256":"87cb7522ab55597de1f284db053381520515c0daa47334c63a5d7d24a9e31f60"},"schema_version":"1.0","source":{"id":"2606.31811","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.31811","created_at":"2026-07-01T01:18:16Z"},{"alias_kind":"arxiv_version","alias_value":"2606.31811v1","created_at":"2026-07-01T01:18:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.31811","created_at":"2026-07-01T01:18:16Z"},{"alias_kind":"pith_short_12","alias_value":"66CYTZEZEZ5U","created_at":"2026-07-01T01:18:16Z"},{"alias_kind":"pith_short_16","alias_value":"66CYTZEZEZ5UMV7P","created_at":"2026-07-01T01:18:16Z"},{"alias_kind":"pith_short_8","alias_value":"66CYTZEZ","created_at":"2026-07-01T01:18:16Z"}],"graph_snapshots":[{"event_id":"sha256:e75cfb5aa9f53b250f2b3e0c3391e71e8ecf340b8cc4b7b9ea2729f8f9a178db","target":"graph","created_at":"2026-07-01T01:18:16Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2606.31811/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Foundation models have transformed vision and language processing by providing rich, reusable representations that transfer across diverse tasks. Sheet music, as a visual encoding of musical language, lacks such a strong domain-specific backbone. We introduce MuSViT (Music Score Vision Transformer): the first foundation vision model for sheet music representation -- a ViT encoder pre-trained via Masked Autoencoders on 9.7 million pages from the IMSLP. To handle the complexity of real-world scores, we adopt a two-stage curriculum: a synthetic warm-up on typeset scores followed by large-scale tr","authors_text":"Antonio Rios-Vila, Carlos Penarrubia, Eliseo Fuentes-Martinez, Francisco J. Castellanos, Jorge Calvo-Zaragoza, Juan C. Martinez-Sevilla, Mar\\'ia Alfaro-Contreras","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-30T15:27:12Z","title":"MuSViT: A Foundation Vision Model for Sheet Music Representation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.31811","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:d6cda6ff93588af4cae37406a7cac19d9ef66f7734c73338ac875ec687d5f70a","target":"record","created_at":"2026-07-01T01:18:16Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"3e19f4f348cc966c3c0d967c28789f1a92548a79fc983b9259ec253597ad8113","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-30T15:27:12Z","title_canon_sha256":"87cb7522ab55597de1f284db053381520515c0daa47334c63a5d7d24a9e31f60"},"schema_version":"1.0","source":{"id":"2606.31811","kind":"arxiv","version":1}},"canonical_sha256":"f78589e499267b4657ef25f001fdc725fde37f0b836af1fd14203c358fee2e57","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f78589e499267b4657ef25f001fdc725fde37f0b836af1fd14203c358fee2e57","first_computed_at":"2026-07-01T01:18:16.356568Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-01T01:18:16.356568Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zF1eA7Duo/kRWHbTiB5HPn8Pw1xfcOjZt5nJzTGN7cDaiJVZNX40lV0Mk1lwWdF23BtZM6+NonwZeINAIeCMDg==","signature_status":"signed_v1","signed_at":"2026-07-01T01:18:16.357108Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.31811","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d6cda6ff93588af4cae37406a7cac19d9ef66f7734c73338ac875ec687d5f70a","sha256:e75cfb5aa9f53b250f2b3e0c3391e71e8ecf340b8cc4b7b9ea2729f8f9a178db"],"state_sha256":"7dbdb1641edce53016b7daa07dfaad1cc1afbc1cfd1370a3d2f96e4e7e96d013"}